Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recommand
    -0.07
     emo
    -0.07
    GetCurrent
    -0.06
     undesirable
    -0.06
     jaz
    -0.06
    -created
    -0.06
    Pure
    -0.06
    .Event
    -0.06
     disclosing
    -0.06
     monthly
    -0.06
    POSITIVE LOGITS
    =t
    0.07
     Reese
    0.07
     ObjectType
    0.06
    _total
    0.06
    =models
    0.06
     Keynes
    0.06
     =
    0.06
     Types
    0.06
    Upload
    0.06
     =[
    0.06
    Act Density 0.056%

    No Known Activations